Live demonstration: A support vector machine based hardware platform for blood pressure prediction

Bo Liang, Kefeng Duan, Qingsong Xie, Mohamed Atef, Zhiliang Qian, Guoxing Wang, Yong Lian

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

In this demonstration, a cuffless blood pressure prediction device using photoplethysmography (PPG) and electrocardiogram (ECG) as inputs is presented. The system implemented a support vector machine (SVM) based prediction model in a heterogeneous DSP and FPGA platform. In the system, the complicated data pre-processing tasks are implemented in a Digital Signal Processor TMDX5535EXDSP. The SVM prediction model is implemented as a hardware accelerator in an Artix-7 FPGA. To verify the model performance and observe the results, we also develop a software GUI for the platform. The users can observe their estimated blood pressures and heart rate on the OLED screen in FPGA board, and the corresponding PPG and ECG waveforms in a desktop PC.

Original languageEnglish
Title of host publicationProceedings - 2016 IEEE Biomedical Circuits and Systems Conference, BioCAS 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages130
Number of pages1
ISBN (Electronic)9781509029594
DOIs
Publication statusPublished - 2016
Externally publishedYes
Event12th IEEE Biomedical Circuits and Systems Conference, BioCAS 2016 - Shanghai, China
Duration: Oct 17 2016Oct 19 2016

Publication series

NameProceedings - 2016 IEEE Biomedical Circuits and Systems Conference, BioCAS 2016

Conference

Conference12th IEEE Biomedical Circuits and Systems Conference, BioCAS 2016
Country/TerritoryChina
CityShanghai
Period10/17/1610/19/16

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Instrumentation
  • Biomedical Engineering

Fingerprint

Dive into the research topics of 'Live demonstration: A support vector machine based hardware platform for blood pressure prediction'. Together they form a unique fingerprint.

Cite this